Filter By Year

1945 2024


Found 205 documents
Search Text-Based Approach

A custom-built deep learning approach for text extraction from identity card images Suddul, Geerish; Seguin, Jean Fabrice Laurent
International Journal of Informatics and Communication Technology (IJ-ICT) Vol 13, No 1: April 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijict.v13i1.pp34-41

Abstract

Information found on an identity card is needed for different essential tasks and manually extracting this information is time consuming, resource exhaustive and may be prone to human error. In this study, an optical character recognition (OCR) approach using deep learning techniques is proposed to automatically extract text related information from the image of an identity card in view of developing an automated client onboarding system. The OCR problem is divided into two main parts. Firstly, a custom-built image segmentation model, based on the U-net architecture, is used to detect the location of the text to be extracted. Secondly, using the location of the identified text fields, a (CRNN) based on long short-term memory (LSTM) cells is trained to recognise the characters and build words. Experimental results, based on the national identity card of the Republic of Mauritius, demonstrate that our approach achieves higher accuracy compared to other studies. Our text detection module has an intersection over union (IOU) measure of 0.70 with a pixel accuracy of 98% for text detection and the text recognition module achieved a mean word recognition accuracy of around 97% on main fields of the identity card.
TEACHING REPORT TEXT BY USING SCIENTIFIC APPROACH WITH DISCOVERY LEARNING STRATEGIES Abdullah Azzam Akbar; Ahmad Syafi'i; Haris Dibdyaningsih
Journal of English Language Teaching and Islamic Integration Vol. 7 No. 1 (2024): JELTII: Journal of English Language Teaching and Islamic Integration
Publisher : STKIP AL HIKMAH SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.10547681

Abstract

A  newly  designed  curriculum  called  as  K-13  (Curriculum  2013)  was  officially implemented in the beginning of 2013. A scientific approach becomes the most significant part of it. Some researchers had researched about implementation of scientific approach in the classroom and they found that the implementation is not optimal. There are many teachers who are not able to implement scientific approach perfectly, the teachers use less than five steps that actually must be implemented in the classroom. Most of teachers had difficulty in implementing scientific approach because they have a little knowledge about it.
THE IMPLEMENTATION OF SCIENTIFIC APPROACH USING DISCOVERY LEARNING IN TEACHING REPORT TEXT Abdullah Azzam Akbar; Ahmad Syafi'i; Haris Dibdyaningsih
Journal of English Language Teaching and Islamic Integration Vol. 6 No. 2 (2023): JELTII: Journal of English Language Teaching and Islamic Integration
Publisher : STKIP AL HIKMAH SURABAYA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.10548474

Abstract

A newly designed curriculum called as K-13 (Curriculum 2013) was officially implemented in the beginning of 2013. A scientific approach becomes the most significant part of it. Five steps of scientific approach such as, observation, questioning, experimenting, associating and communicating will be studied in this research. One of the learning methods that is often used is discovery learning. This study aims to determine how the learning process uses the scientific approach with discovery learning methods in learning report text. Qualitative methods are used to see how this learning takes place. The research subjects were students of SMP IT Ibnu Sina grade 9. To obtain the data, observations, questionnaires and documentation were used. The results of the questionnaire showed that 5.26% (very positive), 56.39% (positive), 35, 33% (quite positive), and finally 3% (not positive). The analysis obtained shows that from the questionnaire given and the results of observations, students have very positive responses to learning using the scientific approach and discovery learning methods. But in practice it is not as easy as imagined. From 5 steps in the scientific approach, only 3 steps can be applied. This is influenced by learning that is carried out online. Suggestions that can be given are the teacher's ability to know what aspects must be considered before teaching and online learning must be better prepared because many materials are not easily explained without meeting students face to face.
CONSTRUCTIVISM APPROACH TO DEVELOP STUDENTS’ CRITICAL THINKING FOR WRITING ANALYTICAL EXPOSITION TEXT Sharizan, Sharizan; Titania, Fani Nabila; Handayani, Riris; Hidayah, Ayu Rahmah
ENGLISH Vol 19 No 1 (2025)
Publisher : Fakultas Keguruan Ilmu Pendidikan Universitas Ibn Khaldun Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research examines the use of the constructivism approach to develop students’ critical thinking for writing analytical exposition texts. This notion appears as the response to the student’s problem in constructing analytical exposition text critically. The primary resources of this literature review research are written and spoken literature. This study explains the foundation of constructivism approach to develop students’ critical thinking for writing analytical exposition texts. According to the discussion of this literature research, the constructivism approach can be used to create essential thinking since it lets the students construct knowledge by themselves from natural and contextual experiences in the field. That is why the constructivist approach has the potential to develop students’ critical thinking while writing analytical exposition texts. However, teachers and students should understand this approach, especially in implementing it, to maximize the use of constructivism for developing critical thinking in writing analytical exposition texts.
An Analysis of Student's Recount Text: An SFL Approach Faradina, Widya Nur; Emilia, Emi
Indonesian Journal of EFL and Linguistics Indonesian Journal of EFL and Linguistics, 9(1), May 2024
Publisher : Pusat Pelatihan, Riset, dan Pembelajaran Bahasa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21462/ijefl.v9i1.751

Abstract

This paper reports on the results of a study aiming to investigate the student’s ability to write recount text of a university student in Bandung. The study was conducted using the theory of Systemic Functional Linguistics (SFL), especially functional grammar, in terms of the Transitivity, Mood and Modality system. The study used a case study on text analysis. A text, which is a recount text written by a higher achiever university student, was analysed using the Transitivity, Mood and Modality system. In terms of the Transitivity system, the result indicates the writer’s adequate syntactic compression and rich lexico-grammatical patterns. Moreover, in terms of the Mood and Modality system, the text shows the writer’s ability to infuse, temper, negotiate, and constrain the experiential meanings in the Mood that is in focus. Hence, the writer is categorized as a mature and critical writer, and the text is appropriate to be used as a model text. Research on text analysis using SFL of different genres of text and how the teaching of writing should be conducted to help improve students’ writing ability is recommended.
A Lesson Learned from BSI Error Service: A Twitter Text Mining Data Approach Using NVivo Izza, Nadia Nurul; Herindar, Evania; Akbar, Nashr
MALIA: Journal of Islamic Banking and Finance Vol 8, No 1 (2024): MALIA: Journal of Islamic Banking and Finance
Publisher : IAIN Kudus

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21043/malia.v8i1.23436

Abstract

This research extensively examines  Twitter trend data related to BSI (Bank Syariah Indonesia) error services, collecting 1,014 tweets in real-time using NCapture from NVivo 12 Plus within the timeframe of May 8-16, 2023. The key findings highlight that 81% of conversations regarding BSI error services carry a negative sentiment. Additionally, a word cloud identifies key terms such as "services" (2.21%), "transactions" (0.87%), "ransomware" (0.74%), and "trust" (0.42%). As a concrete solution, the research recommends enhancing the transparency of BSI management to the public and fostering close collaboration with relevant authorities such as OJK, BI, and LPS. Furthermore, the strengthening of BSI's cybersecurity is emphasized to mitigate risks. These findings not only provide in-depth insights but also present practical steps that can be implemented to protect consumers and restore public trust in the Islamic banking sector. As a valuable contribution to the literature, this research not only offers a snapshot of the current situation but also identifies relevant directions for future research. Overall, the study integrates comprehensive data analysis with impactful recommendations, establishing a robust foundation for understanding and continuous improvement in the management of BSI error services. Notably, this research is the first to use NVivo in collecting Twitter data related to BSI error services
Evaluating the Impact of Digital Transformation and Sustainability Strategies on Earnings Management: A Text Mining Approach Wibowo, Agung Septia; Istianah, Iis; Sari, Nia Pramita; Septiari, Dovi
Asia Pacific Fraud Journal Vol. 9 No. 1: 1st Edition (January-June 2024)
Publisher : Association of Certified Fraud Examiners Indonesia Chapter

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21532/apfjournal.v9i1.339

Abstract

Digital transformation has the potential to fundamentally change companies and create value. This study examines the impact of digital transformation and sustainability strategies on the earnings quality of Indonesian listed companies on three sectors: infrastructures, transportation and logistics, and consumer non-cyclicals. Using text mining techniques to measure intensity of digital transformation and sustainability strategies, we found that sustainability strategy shown in the company’s annual report reflects lower level of earnings management especially in accrual earnings management, while companies with digital transformation strategy, particularly in artificial intelligence technology, are less likely to engage real earnings management. Findings of this study provide insights into the effect of digital transformation and sustainability on the quality of accounting information and corporate governance, and offer implications for corporate digital transformation and government regulation.
Literature Reviews of RBV and KBV Theories Reimagined - A Technological Approach Using Text Analysis and Power BI Visualization Arief, Ikhwan; Hasan, Alizar; Putri, Nilda Tri; Rahman, Hafiz
JOIV : International Journal on Informatics Visualization Vol 7, No 4 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.7.4.1940

Abstract

Over the years, the Resource-Based View (RBV) and Knowledge-Based View (KBV) have solidified their roles as pivotal paradigms in strategic management literature. With an emphasis on Small and Medium Enterprises (SMEs), this study uses text analysis and Microsoft Power BI to explore these concepts innovatively. The study implements a systematic literature review, extracting data from Scopus, Web of Science, and DOAJ databases to assemble a comprehensive literature corpus. The methodology incorporates text analysis to draw out key themes, relationships, and trends, and these are subsequently visualized using Power BI to create an engaging, interactive representation of data. Components like word clouds, co-occurrence networks, and trend lines are generated, while Power BI's dynamic filtering and drill-down functionalities facilitate thorough data investigation. The results display significant overlap between RBV and KBV, denoting possible integration junctures for these theories within the domain of strategic management. Additionally, the study underscores the relevance of these insights for SMEs, emphasizing the part played by unique resources, encompassing knowledge assets, in catalyzing innovation and fostering a competitive edge. The study concludes by recognizing the significant theoretical and practical implications of integrating text analysis and Power BI in conducting literature reviews. This methodology bolsters our understanding of RBV and KBV, offering small and medium-sized enterprises a beneficial instrument to traverse these intricate theories. The study suggests that future research could broaden the application of this methodological approach to encompass other strategic management theories.
Analysis Voting Sentiment In The 2024 Election Via Twitter Text Mining And K-Means Classification Approach Lubis, Ahmad Raihan; Hutagalung , Fatma Sari
Bahasa Indonesia Vol 16 No 03 (2024): Instal : Jurnal Komputer
Publisher : Cattleya Darmaya Fortuna

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54209/jurnalinstall.v16i03.228

Abstract

This research examines opinion sentiment regarding (1) voters in the 2024 election using data analysis from the social media Twitter. (2) Using a text mining and classification approach, (1) this research extracts valuable information from tweets containing keywords related to the 2024 election. The data collection process is carried out using scraping techniques, where tweets are collected within a certain period of time to ensure complete representation. After the data is collected, (2) preprocessing is carried out to clean and prepare the text, which includes steps such as tokenaize, stopword and labeling. (1) Sentiment analysis is then used to categorize tweets into positive, negative or neutral sentiment. (2) The K-Means algorithm is used to collect opinion data to help identify patterns and trends in public perception of political candidates and issues. (1) Analysis results shows that there is a significant distribution of opinions between different candidates and issues, thus revealing the complex dynamics of public opinion. (2)These results provide policymakers, political candidates, and researchers with an in-depth understanding of how public opinion is formed and how it can be influenced during election campaigns. Additionally, this research highlights the great potential of applying text mining technologies and algorithms
A Text Mining Approach to Analyzing the Omnichannel Retail Business Performance of the KlikIndomaret App Budianto, Akhmad Ghiffary; Suryo, Arief Trisno Eko; Zulkarnain, Andry Fajar; Cahyono, Gunawan Rudi; Rusilawati, Rusilawati; Az-Zahra, Siti Fatimah
Jurnal Teknik Industri: Jurnal Keilmuan dan Aplikasi Teknik Industri Vol. 26 No. 2 (2024): December 2024
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9744/jti.26.2.131-144

Abstract

The evolution of Web 2.0 technology has significantly influenced the use of Android applications, enabling users to provide feedback through reviews and star ratings. In managing omnichannel retail businesses, this user-generated content serves as a valuable source of information for performance evaluation and strategic management of both online and offline operations. Large-scale user review data is well-suited for analysis through text mining, particularly in sentiment analysis, when combined with topic and keyword filtering in the business domain. This study utilizes the RoBERTa Transformer model for the sentiment classification of user reviews. Among the 520 user reviews, 211 displayed good emotion, while 309 showed negative sentiment. By applying filtering processes to topics and keywords within the omnichannel retail business domain, the study identifies "economic value" and "delivery and CRM" as priority areas for improvement. This conclusion is drawn based on the significant disparity between positive and negative sentiments. As a result, management can formulate strategies to enhance the performance and user experience of the KlikIndomaret Android application.

Page 15 of 21 | Total Record : 205